def computeLowLevel(input_file,
neqPool,
eqPool,
startTime,
endTime,
namespace=''):
llspace = 'lowlevel.'
rhythmspace = 'rhythm.'
if namespace:
llspace = namespace + '.lowlevel.'
rhythmspace = namespace + '.rhythm.'
rgain, sampleRate, downmix = getAnalysisMetadata(neqPool)
loader = streaming.EasyLoader(filename=input_file,
sampleRate=sampleRate,
startTime=startTime,
endTime=endTime,
replayGain=rgain,
downmix=downmix)
eqloud = streaming.EqualLoudness()
loader.audio >> eqloud.signal
lowlevel.compute(eqloud.signal, loader.audio, neqPool, startTime, endTime,
namespace)
lowlevel.compute(eqloud.signal, eqloud.signal, eqPool, startTime, endTime,
namespace)
essentia.run(loader)
# check if we processed enough audio for it to be useful, in particular did
# we manage to get an estimation for the loudness (2 seconds required)
if not neqPool.containsKey(llspace + "loudness") and\
not eqPool.containsKey(llspace + "loudness"):
INFO('ERROR: File is too short (< 2sec)... Aborting...')
sys.exit(2)
sampleRate = neqPool['metadata.audio_properties.analysis_sample_rate']
numOnsets = len(neqPool[rhythmspace + 'onset_times'])
onset_rate = numOnsets / float(loader.audio.totalProduced()) * sampleRate
neqPool.set(rhythmspace + 'onset_rate', onset_rate)
numOnsets = len(eqPool[rhythmspace + 'onset_times'])
onset_rate = numOnsets / float(loader.audio.totalProduced()) * sampleRate
eqPool.set(rhythmspace + 'onset_rate', onset_rate)
def computeMidLevel(input_file,
neqPool,
eqPool,
startTime,
endTime,
namespace=''):
rgain, sampleRate, downmix = getAnalysisMetadata(neqPool)
loader = streaming.EasyLoader(filename=input_file,
sampleRate=sampleRate,
startTime=startTime,
endTime=endTime,
replayGain=rgain,
downmix=downmix)
eqloud = streaming.EqualLoudness()
loader.audio >> eqloud.signal
midlevel.compute(loader.audio, neqPool, startTime, endTime, namespace)
midlevel.compute(eqloud.signal, eqPool, startTime, endTime, namespace)
essentia.run(loader)
def computeNoveltyCurve(self,
filename,
frameSize=1024,
hopSize=512,
windowType='hann',
weightCurveType='hybrid',
sampleRate=44100.0,
startTime=0,
endTime=2000):
loader = ess.EasyLoader(filename=filename,
startTime=startTime,
endTime=endTime,
sampleRate=sampleRate,
downmix='left')
fc = ess.FrameCutter(frameSize=frameSize,
hopSize=hopSize,
silentFrames="keep",
startFromZero=False,
lastFrameToEndOfFile=True)
window = ess.Windowing(type=windowType,
zeroPhase=True,
zeroPadding=1024 - frameSize)
freqBands = ess.FrequencyBands(
sampleRate=sampleRate) # using barkbands by default
spec = ess.Spectrum()
pool = Pool()
loader.audio >> fc.signal
fc.frame >> window.frame >> spec.frame
spec.spectrum >> freqBands.spectrum
freqBands.bands >> (pool, 'frequency_bands')
essentia.run(loader)
noveltyCurve = NoveltyCurve(frameRate=sampleRate / float(hopSize),
weightCurveType=weightCurveType)(
pool['frequency_bands'])
return noveltyCurve
